ES

About me

I am Head of AI GTM Engineering at Sesame HR. But before this, in London, I was Global Lead of automation and technology at Dentsu, and later I co-founded a conversational AI startup. Along the way I learned to see every company as a system of business, people, tools and AI, and my work is to make it programmable.

What a programmable organization looks like

The way I see it, a company is a system that AI makes programmable, which means its processes are in view and change under control. In every area, AI agents do part of the work, people bring judgement where it matters, and someone decides what gets built and answers for the result. That is what I apply every day at Sesame HR, in five markets, and at other companies that work with me.

Each agent or tool specializes in one thing and is part of a chain, because it uses what others produce and in turn feeds other flows. And since they are gears of the same engine, each decision can be made with better information.

Portrait of Ibán Ríos in a grey blazer and white shirt

Ibán: decides and is accountable

I decide what gets built, set the rules the agents work under, and answer for the result.

This is a conceptual example, not a diagram of a real company, so take it as an idea of what it could look like, area by area:

  • Marketing

    One agent watches the campaigns and another prepares ads and content in several languages, and what they both learn then flows to sales and data.

    People choose the message and the budget, and approve what gets published.

  • Sales and revenue

    An agent gives the sales team a hand: it qualifies every lead using what marketing already knows, passes it to whoever should take it, and can even close simple sales. And every closed deal goes back to marketing to sharpen who to look for.

    Salespeople own the conversations and the deals that matter.

  • Data and market

    One agent tracks competitors and another measures which channel brings revenue, so the other areas draw on this and leaders ask it questions in plain language.

    Leaders decide what the numbers mean and what to do next.

  • Internal tools

    Agents build and look after the portals and tools that connect each piece to the others.

    The teams that use them say what they need and whether it works.

  • Quality and security

    An agent checks every change, whichever area it comes from, before it goes live, and keeps keys and permissions locked down.

    A person sets the rules, not an agent, and only a person can loosen them.

  • Research

    An agent reads documentation, regulation and new tools, and writes down what it learns for the others to use.

    A person decides, not an agent, and answers for the decision.

What stays human

  • Strategy: deciding what matters and what to leave out.
  • Judgement: knowing when an answer is wrong, even if it looks right.
  • Relationships with customers, colleagues and partners.
  • Taste and new ideas.
  • Leading the people who work around the system.
  • Answering for the result.

The difference between a demo and a reliable system

Today anyone can ask an AI for a website, a chatbot or an agent, and have it working by the evening. Accepting what it produces like that, without reading or testing it, is what people call vibe coding. For a prototype it can be fine, but for something that touches customer data, money or your company's name, I would not risk it.

And watch out, because an agent reads emails, web pages and documents, and if one of them carries hidden instructions, a badly built agent follows them without a second thought. This is called prompt injection, and no single trick fixes it. What does help is how it is built: each agent with only the permissions it needs, anything from outside treated as information and not as orders, and everything logged.

Why me

I have worked in agencies and in large companies, across marketing, revenue and product, and at Dentsu International I ran the automations for the whole network from London. Then, in 2021 and before ChatGPT came along, I co-founded and led Chat Ergo Bot, a startup for building chatbots with AI.

Today I take care of Sesame HR's internal AI projects, treating each team as a client: I build on its real data and measure myself by its result. And outside Sesame HR I teach at EDEM and build my own products, such as ValidWise and Privacy Guard.

Why this is not vibe coding

A demo built with AI can hold up for a while, but when it fails, it is usually with your data or your customers'. So here are the four differences that, to my mind, matter most.

  • Security and data

    Vibe coding

    Keys often end up inside the code, the agent obeys instructions hidden in an email, and customer data travels to unreviewed tools.

    How I do it

    Keys stay out of the code, each agent can do only what its task requires, and what arrives from outside is not treated as an order. And GDPR and the AI Act are part of the design from the start.

  • Reliability

    Vibe coding

    It works in the demo and with ten users, but with real customers it falls over.

    How I do it

    I put in automatic tests, usage limits and cost measured per task, and every change passes checks before it goes live. I have been building systems for more than ten years, so I know where they tend to break.

  • Maintenance and traceability

    Vibe coding

    Each automation runs on its own, so when it fails it is hard to tell what it did or why, and touching it feels risky.

    How I do it

    Every piece is documented, tested and connected to the others, and there is a record of what each agent does, why, and what it costs. And what no longer serves is retired.

  • Business judgement

    Vibe coding

    It solves the task you asked for with the tool it knows, without seeing the rest of the company.

    How I do it

    Because I have worked in business, marketing, sales and product, I see how each piece affects the others before I build it. And keeping up with AI is part of my job.

How I work

My team: me and my AI agents

I work with AI agents that build, review and research, and each one has a role and limits it cannot skip. Above them, I decide and answer to you.

Portrait of Ibán Ríos in a grey blazer and white shirt

Ibán: decides and is accountable

I understand how your company works, decide what gets built and how, and answer to you for the result. I also set the rules below, and the agents cannot loosen them.

  • Builder agent

    Writes the code, the tests and the documentation for each change.

    Cannot approve its own work, because it is judged by tests it cannot touch.

  • Reviewer agents

    Read the sensitive changes that others wrote, looking for bugs and risks.

    Can only read: they do not touch the code they review.

  • Research agent

    Reads documentation, regulation and tools before anything is decided.

    Installs nothing, and what it proposes does not go in without my go-ahead.

  • Automated checks

    Check every change: security, accessibility, speed and that nothing breaks.

    Can only get stricter, and loosening them takes a decision of mine in writing.

The team's rules

  • No key or password in sight: not in the code, not in messages, not in logs.
  • Agents work in isolation, with only the permissions they need.
  • Nothing goes live without passing the automated checks.
  • If something breaks when it goes live, it gets fixed or rolled back.
  • Every change is on record: what was done, why and who asked for it.

Journey

Oxford to London

2014–2020

This part of the story starts in Oxford, where I turned a side interest into my job and went from webmaster to manager at OISE Languages in under a year.

Then came London, where I did paid search at PHD Media (Omnicom) for Unilever and Upfield, and independent performance marketing for MOBS Shoes. From there I moved to Dentsu International, one of the big media agency networks, where I was Global Lead, Automation & Tech across Dentsu X and iProspect. There I worked for Apple, Square, HTC and Le Creuset.

At PHD Media I was Employee of the Month, and in the Dentsu International PPC community, Star of 2019.

And it was at Dentsu that I built GeoAdsFinder, a tool to check search results that was adopted across the network and still carries on as a standalone product.

Founder

2021–2023

In 2021 I co-founded and led Chat Ergo Bot, a platform for building chatbots with conversational AI, and with it we arrived early, before ChatGPT existed.

It all started in 2020 with #YoMeTesteoEnCasa, a COVID-19 self-assessment test for the whole of Spain. We built it in 24 hours to take pressure off emergency phone lines that were overwhelmed, and Chat Ergo Bot grew out of it.

Along the way, El Referente named us among the Top 75 startups of Spain and Portugal in 2022, we were Planeta Chatbot finalists, and in 2023 Lanzadera selected us.

Even so, Chat Ergo Bot closed in 2023 because of a co-founder disagreement and the upheaval large language models brought to the market. But the idea was not wrong, and in fact it lives on in AIsWise.

Sesame HR

2023–now

In August 2023 I joined Sesame HR as Senior Paid Media & Marketing Operations Specialist, and thirteen months later I was Head of Paid Media & Marketing Operations.

MVP of 2024, company-wide across 370 employees, and PPC King in Q1 2024.

There I came to manage over €600K a month in paid media across five markets. And along the way I rebuilt how campaigns are tagged and tracked, led the move to Google's Consent Mode v2 and built attribution across ad platforms.

Building at scale

2025–now

From December 2025 to April 2026 I was interim Head of Demand Generation & Growth, with a twelve-person team across five countries.

And since April 2026 I have been the first Head of AI GTM Engineering at Sesame HR, with a mandate over internal AI projects across the company. In this role I report directly to the CRO, the COO and the CEO.

Alongside that, I have three products of my own live (GeoAdsFinder, AIsWise and ValidWise), plus SOVEREIGN, the method this site is built with.

And I am also a visiting lecturer at EDEM business school, teaching some of the AI subjects of its Master's in UX/UI Design, AI and Digital Strategy.

Leadership and scope

What I answer for today, and what I answered for before.

  • Scope

    Internal AI projects across the whole of Sesame HR, as its first Head of AI GTM Engineering.

  • People

    Interim head of a twelve-person Demand Generation team across five countries, from December 2025 to April 2026. Before that, in London, I trained the search teams across the Dentsu network in automation.

  • Markets

    Five markets at Sesame HR. From London, Apple worldwide, Square in the UK and Unilever in Europe.

  • Stakeholders

    I report to the CRO, the COO and the CEO, and work with sales, finance, customer success and marketing.

  • Decisions

    What gets built and in what order in the company's internal AI projects, and the rules every agent works under.

  • Impact

    Ten-plus internal tools in production and the company's MVP of 2024.

What I've built

Independent products and projects I have launched

GeoAdsFinder

For SEO and paid search teams. It shows what someone searching Google from any city or country sees, ads included, and lets you see competitors' ads on Meta, Google, TikTok and LinkedIn. It was born at Dentsu International for a problem the whole network had, and the network ended up adopting it. Today it is a standalone product, free in its basic version, that now also covers visibility in AI search.

AIsWise

For companies that want their website to serve everyone by voice and text, people with disabilities included. Today it offers AI assistants with WCAG 2.2 accessibility built in. And what is in development is fixing a website's accessibility barriers faster, with a before-and-after audit as proof. It grew out of Chat Ergo Bot, the startup I co-founded in 2021.

ValidWise

For companies with a website in Europe that want to know what they are missing to comply. It checks a website with 70 automated tests in five groups: accessibility (EAA, 30), GDPR (15), security headers (14), the AI Act (5) and legal requirements (6). Bear in mind that it finds issues but does not certify compliance.

SOVEREIGN

It is my method for building software with AI, where every step passes automated checks and the agent that builds cannot sign off its own work. And this very site is built with it.

Privacy Guard

For anyone who wants to know whether someone is watching their Mac. It is a free menu-bar app for macOS that detects what monitoring or management software is installed, company or personal. And it does so without admin rights and without sending anything over the internet.

#YoMeTesteoEnCasa

An online test that let anyone in Spain run a COVID-19 self-assessment, which I built in 2020 with two friends in 24 hours. Each person answered a few questions and got the next steps and the emergency contacts for their region. It was unofficial and non-profit, and Expansión and Xataka, among others, covered it.

What I build inside Sesame HR and for my clients belongs to them and is not sold elsewhere. But there are examples above, in “What a programmable organization looks like” and in “My team”.

Recognition

  • MVP of 2024 · Sesame HR, company-wide across 370 employees
  • PPC King, Q1 2024 · Sesame HR
  • Star of 2019 · Dentsu International PPC community
  • New Employee of the Year, nomination · Dentsu X, 2019
  • Constructive Rebellion, nomination · Dentsu X
  • Employee of the Month · PHD Media / Omnicom, March 2018
  • Top Paid Media Specialist · Mayple
  • Lanzadera Selection 2023 · for Chat Ergo Bot
  • Top 75 Startups of Spain and Portugal 2022 · El Referente, for Chat Ergo Bot
  • Planeta Chatbot Finalist · for Chat Ergo Bot

Questions about me

Who is Ibán Ríos?

Ibán Ríos is Head of AI GTM Engineering at Sesame HR, based in Valencia, Spain. He builds AI agents, automations or software that do real tasks for companies. Before that he worked in London, where he did paid search at PHD Media (Omnicom) and was Global Lead, Automation & Tech at Dentsu International. Then in 2021, before ChatGPT, he co-founded and led Chat Ergo Bot, a conversational AI startup. Today he is also a visiting lecturer at EDEM business school and builds independent products such as GeoAdsFinder, AIsWise and ValidWise.

What is AI GTM Engineering?

AI GTM Engineering means designing, building and running the systems a company uses to sell and grow the way software is built, with more and more AI inside them. GTM stands for go-to-market, that is, everything a company does to take a product to market and sell it. Ibán Ríos is responsible for the internal AI projects at Sesame HR. And there he starts from the idea that any process where information passes from one person or tool to another can be designed as a system.

What does a programmable organization mean?

A programmable organization is one that keeps its processes in view, so it can change them with control and improve them. It starts from the idea that organizations are systems, and that way it stops relying on manual steps only a few people know.

What is an AI agent?

An AI agent is a program that does a whole task on its own: it reads the information it needs, decides within a set of rules and acts. It also leaves a trail, so a person can see what it did and why. Unlike a generic chatbot or a demo, it works inside a real process, with real data and someone responsible for the result.

What is a forward deployed engineer?

An engineer who works inside the client's company, with its team and real data, and builds what that client needs until it works. That is why they are judged by the client's result more than by the code they ship. The term comes from Palantir, and Ibán Ríos works this way: the build phase has an end date, and afterwards he looks after maintenance.

What AI training does Ibán Ríos teach?

He teaches applied AI for teams: how to use it well in their work, how to build their own tools and software with AI, best practices and tips. It includes AI literacy, in line with Article 4 of the AI Act, and safe use of AI at work: an approved tool, a usage policy and data protection. He is also a visiting lecturer at EDEM business school, where he teaches some of the AI subjects of the Master's in UX/UI Design, AI and Digital Strategy. And from 2027 he will also teach at the Chamber of Commerce business school.

What brands has Ibán Ríos worked with?

Apple, Square, HTC and Le Creuset, through Dentsu International, where he worked closely with Google. Before that, Unilever and Upfield through PHD Media (Omnicom), and MOBS Shoes as an independent client. Today he works at Sesame HR, closely with Meta.

Got a task you want to hand to AI?

Tell me what the task is and how it is done today, and I will tell you where I would start.

Tell me which task you want to hand over